Motion Estimation Todays Readings Trucco Verri, 8.3 8.4 (skip 8.3.3, read only top half of p. 199)...
-
Upload
percival-rogers -
Category
Documents
-
view
217 -
download
0
description
Transcript of Motion Estimation Todays Readings Trucco Verri, 8.3 8.4 (skip 8.3.3, read only top half of p. 199)...
Motion Estimation
Today’s Readings• Trucco & Verri, 8.3 – 8.4 (skip 8.3.3, read only top half of p. 199)• Newton's method Wikpedia page
http://www.sandlotscience.com/Distortions/Breathing_Square.htm
http://www.sandlotscience.com/Ambiguous/Barberpole_Illusion.htm
Copyright A.Kitaoka 2003
Why estimate motion?Lots of uses
• Track object behavior• Correct for camera jitter (stabilization)• Align images (mosaics)• 3D shape reconstruction• Special effects• Video slow motion• Video super-resolution
Motion estimationInput: sequence of imagesOutput: point correspondence
Feature tracking• we’ve seen this already (e.g., SIFT)• can modify this to be more efficient
Pixel tracking: “Optical Flow”• today’s lecture
Optical flow
Problem definition: optical flow
How to estimate pixel motion from image H to image I?• Solve pixel correspondence problem– given a pixel in H, look for nearby pixels of the same color in I
Key assumptions• color constancy: a point in H looks the same in I– For grayscale images, this is brightness constancy• small motion: points do not move very far
This is called the optical flow problem
Optical flow constraints (grayscale images)
Let’s look at these constraints more closely• brightness constancy: Q: what’s the equation?
• small motion: (u and v are less than 1 pixel)– suppose we take the Taylor series expansion of I:
Optical flow equationCombining these two equations
In the limit as u and v go to zero, this becomes exact
Optical flow equation
Q: how many unknowns and equations per pixel?
Intuitively, what does this constraint mean?
• The component of the flow in the gradient direction is determined• The component of the flow parallel to an edge is unknown
This explains the Barber Pole illusionhttp://www.sandlotscience.com/Ambiguous/Barberpole_Illusion.htm
Example on the board
Aperture problem
Aperture problem
Solving the aperture problemHow to get more equations for a pixel?
• Basic idea: impose additional constraints– most common is to assume that the flow field is smooth locally– one method: pretend the pixel’s neighbors have the same (u,v)
» If we use a 5x5 window, that gives us 25 equations per pixel!
Lucas-Kanade flowProb: we have more equations than unknowns
• The summations are over all pixels in the K x K window• This technique was first proposed by Lucas & Kanade (1981)
Solution: solve least squares problem• minimum least squares solution given by solution (in d) of:
Conditions for solvability• Optimal (u, v) satisfies Lucas-Kanade equation
When is This Solvable?• ATA should be invertible • ATA should not be too small due to noise– eigenvalues λ1 and λ2 of ATA should not be too small• ATA should be well-conditioned– λ1/ λ2 should not be too large (λ1 = larger eigenvalue)
Does this look familiar?• ATA is the Harris matrix
15
16
17
ObservationThis is a two image problem BUT
• Can measure sensitivity by just looking at one of the images!• This tells us which pixels are easy to track, which are hard
– very useful later on when we do feature tracking...
Errors in Lucas-KanadeWhat are the potential causes of errors in this procedure?
• Suppose ATA is easily invertible• Suppose there is not much noise in the image
When our assumptions are violated• Brightness constancy is not satisfied• The motion is not small• A point does not move like its neighbors– window size is too large
• Can solve using Newton’s method– Also known as Newton-Raphson method• Approach so far does one iteration of Newton’s method– Better results are obtained via more iterations
Improving accuracyRecall our small motion assumption
This is not exact• To do better, we need to add higher order terms back in:
This is a polynomial root finding problem1D caseon board
Iterative RefinementIterative Lucas-Kanade Algorithm1. Estimate velocity at each pixel by solving Lucas-Kanade equations2. Warp H towards I using the estimated flow field- use image warping techniques3. Repeat until convergence
Revisiting the small motion assumption
Is this motion small enough?• Probably not—it’s much larger than one pixel (2nd order terms dominate)• How might we solve this problem?
23
Reduce the resolution!
image Iimage H
Gaussian pyramid of image H Gaussian pyramid of image I
image Iimage H u=10 pixels
u=5 pixels
u=2.5 pixels
u=1.25 pixels
Coarse-to-fine optical flow estimation
image Iimage J
Gaussian pyramid of image H Gaussian pyramid of image I
image Iimage H
Coarse-to-fine optical flow estimation
run iterative L-K
run iterative L-K
warp & upsample
.
.
.
Flow quality evaluation
Flow quality evaluation
Flow quality evaluationMiddlebury flow page
• http://vision.middlebury.edu/flow/
Ground Truth
Flow quality evaluationMiddlebury flow page
• http://vision.middlebury.edu/flow/
Ground TruthLucas-Kanade flow
Flow quality evaluationMiddlebury flow page
• http://vision.middlebury.edu/flow/
Ground TruthBest-in-class alg